Autonomous welding robots

Abstract

In some examples, an autonomous robotic welding system comprises a workspace including a part having a seam, a sensor configured to capture multiple images within the workspace, a robot configured to lay weld along the seam, and a controller. The controller is configured to identify the seam on the part in the workspace based on the multiple images, plan a path for the robot to follow when welding the seam, the path including multiple different configurations of the robot, and instruct the robot to weld the seam according to the planned path.

What is claimed is: 
     
       1. A welding robotic system, comprising:
 one or more sensors configured to capture multiple images related to a first part and a second part, the first part and second part positioned within a manufacturing workspace to form a seam, wherein at least a portion of the seam is to be welded using a welding tool configured to perform a welding operation, and wherein the welding tool is coupled to a robotic arm configured to move the welding tool; and 
 a robot controller configured to:
 detect an expected position of the seam based on a Computer Aided Design (CAD) model including a first representation of the first part and a second representation of the second part; 
 determine a location of the first and second parts within the manufacturing workspace using the multiple images; 
 identify an actual position of the seam along which the welding operation is to be performed; 
 generate motion parameters for the robotic arm for performance of the welding operation at least along the portion of the seam; and 
 weld the first and second parts together at the actual position of the seam using the motion parameters for the robotic arm. 
 
 
     
     
       2. The welding robotic system of  claim 1 , wherein the seam includes:
 one or more tack welds at least partially connecting the first part and the second part; or 
 an unwelded seam forming the portion of the seam. 
 
     
     
       3. The welding robotic system of  claim 2 , wherein the seam includes the one or more tack welds and the unwelded seam. 
     
     
       4. The welding robotic system of  claim 1 , further comprising at least one additional sensor coupled to the welding tool. 
     
     
       5. The welding robotic system of  claim 4 , wherein, to determine the actual position of the seam, the robot controller is configured to update the expected position of the seam based on data generated by the at least one additional sensor. 
     
     
       6. The welding robotic system of  claim 1 , wherein the CAD model includes an annotation of the seam. 
     
     
       7. A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform operations comprising:
 detecting an expected position of a seam based on a Computer Aided Design (CAD) model including a first representation of a first part and a second representation of a second part, the seam formed between the first part and the second part; 
 determining a location of the first and second parts within a manufacturing workspace using multiple images captured by one or more sensors; 
 identifying an actual position of the seam along which a welding operation is to be performed; 
 generating motion parameters for a robotic arm for performance of the welding operation at least along a portion of the seam; and 
 initiating welding the first and second parts together at the actual position of the seam using the motion parameters for the robotic arm. 
 
     
     
       8. The non-transitory computer-readable medium of  claim 7 , wherein the seam includes:
 one or more tack welds at least partially connecting the first part and the second part; or 
 an unwelded seam forming the portion of the seam. 
 
     
     
       9. The non-transitory computer-readable medium of  claim 8 , wherein the seam includes the one or more tack welds and the unwelded seam. 
     
     
       10. The non-transitory computer-readable medium of  claim 7 , further comprising at least one additional sensor coupled to a welding tool, the welding tool coupled to the robotic arm. 
     
     
       11. The non-transitory computer-readable medium of  claim 7 , wherein determining the actual position of the seam includes updating the expected position of the seam based on data generated by at least one additional sensor. 
     
     
       12. The non-transitory computer-readable medium of  claim 7 , wherein the CAD model includes an annotation of the seam. 
     
     
       13. A welding robotic system, comprising:
 one or more sensors configured to capture multiple images related to a first part and a second part, the first part and second part positioned to form a seam having a variable gap along a length of the seam, wherein at least a portion of the seam is to be welded using a welding tool configured to perform a welding operation, and wherein the welding tool is coupled to a robotic arm configured to move the welding tool; and 
 a robot controller configured to:
 detect an expected position of the seam based on a Computer Aided Design (CAD) model including a first representation of the first part and a second representation of the second part; 
 identify an actual position of the seam along which the welding operation is to be performed; 
 identify gap variability in the seam along which the welding operation is to be performed; 
 generate welding parameters for the welding tool for performance of the welding operation at least along the portion of the seam, wherein the welding parameters are generated in accordance with the identified gap variability in the seam; and 
 weld the first and second parts using the welding parameters. 
 
 
     
     
       14. The welding robotic system of  claim 13 , wherein the robotic controller is further configured to determine a location of the first and second parts within a manufacturing workspace using the multiple images. 
     
     
       15. The welding robotic system of  claim 13 , wherein the robot controller is further configured to identify gap variability in the seam in accordance with the multiple images. 
     
     
       16. The welding robotic system of  claim 1 , further comprising:
 at least one additional sensor configured to capture one or more images, and 
 wherein the robot controller is configured to identify gap variability in the seam in accordance with the one or more images captured by the at least one additional sensor. 
 
     
     
       17. The welding robotic system of  claim 13 , wherein the robot controller is further configured to:
 determine a location of the first and second parts within a manufacturing workspace using the multiple images. 
 
     
     
       18. The welding robotic system of  claim 17 , wherein the robot controller is configured to identify gap variability at the actual position. 
     
     
       19. A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform operations comprising:
 detecting an expected position of a seam based on a Computer Aided Design (CAD) model including a first representation of a first part and a second representation of a second part; 
 identifying an actual position of the seam along which a welding operation is to be performed; 
 identifying gap variability in the seam along which the welding operation is to be performed, the seam formed between the first part and the second part, wherein the seam has a variable gap along a length of the seam; 
 generating welding parameters for a welding tool for performance of the welding operation at least along a portion of the seam, wherein the welding parameters are generated in accordance with the identified gap variability in the seam; and 
 welding the first and second parts using the welding parameters. 
 
     
     
       20. The non-transitory computer-readable medium of  claim 19 , further comprising:
 determining a location of the first and second parts within a manufacturing workspace using multiple images captured using one or more sensors.